LaVAN: Localized and Visible Adversarial Noise

01/08/2018
by   Danny Karmon, et al.
0

Most works on adversarial examples for deep-learning based image classifiers use noise that, while small, covers the entire image. We explore the case where the noise is allowed to be visible but confined to a small, localized patch of the image, without covering any of the main object(s) in the image. We show that it is possible to generate localized adversarial noises that cover only 2 of the pixels in the image, none of them over the main object, and that are transferable across images and locations, and successfully fool a state-of-the-art Inception v3 model with very high success rates.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset